# Hugging Face — LFM2.5-Encoders for Fast Long-Context Inference on CPU

- Company: Hugging Face (huggingface.co)
- Announced: 2026-07-28T15:01:45+00:00
- Category: open-weight-release
- Subject: Platform
- Models affected: LFM2.5-Encoder-230M, LFM2.5-Encoder-350M
- Context window: 8,192-token context
- Source: https://huggingface.co/blog/LiquidAI/lfm2-5-encoders
- Record: https://forck.live/items/1449-lfm2-5-encoders-for-fast-long-context-inference-on-cpu

Hugging Face (with LiquidAI) releases two new encoder models, LFM2.5-Encoder-230M and LFM2.5-Encoder-350M, designed for fast long-context inference on CPU, matching larger models with an 8,192-token context and improved latency.

## Evidence

Verbatim from https://huggingface.co/blog/LiquidAI/lfm2-5-encoders:

> Today, we release two new encoder models on Hugging Face: LFM2.5-Encoder-230M and LFM2.5-Encoder-350M.

---

Record: https://forck.live/items/1449-lfm2-5-encoders-for-fast-long-context-inference-on-cpu
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md